1532-2890/asset/olbannerleft.gif?v=1&s=d833098325c9f1060bcbee51adf276c155608167)
1532-2890/asset/olbannercenter.gif?v=1&s=661179918edb4fa732edfd3408eb050a6ce87809)
1532-2890/asset/olbannerright.gif?v=1&s=1ef8a363944134c502cbffa1937878a71b4cc635)
Research Articles
Classification and powerlaws: The logarithmic transformation
Article first published online: 29 JUN 2006
DOI: 10.1002/asi.20467
Copyright © 2006 Wiley Periodicals, Inc., A Wiley Company
Issue
Journal of the American Society for Information Science and Technology
Volume 57, Issue 11, pages 1470–1486, September 2006
Additional Information
How to Cite
Leydesdorff, L. and Bensman, S. (2006), Classification and powerlaws: The logarithmic transformation. J. Am. Soc. Inf. Sci., 57: 1470–1486. doi: 10.1002/asi.20467
Publication History
- Issue published online: 8 AUG 2006
- Article first published online: 29 JUN 2006
- Manuscript Accepted: 14 SEP 2005
- Manuscript Revised: 13 SEP 2005
- Manuscript Received: 25 JAN 2005
- Abstract
- Article
- References
- Cited By
Abstract
Logarithmic transformation of the data has been recommended by the literature in the case of highly skewed distributions such as those commonly found in information science. The purpose of the transformation is to make the data conform to the lognormal law of error for inferential purposes. How does this transformation affect the analysis? We factor analyze and visualize the citation environment of the Journal of the American Chemical Society (JACS) before and after a logarithmic transformation. The transformation strongly reduces the variance necessary for classificatory purposes and therefore is counterproductive to the purposes of the descriptive statistics. We recommend against the logarithmic transformation when sets cannot be defined unambiguously. The intellectual organization of the sciences is reflected in the curvilinear parts of the citation distributions while negative powerlaws fit excellently to the tails of the distributions.